CN116703182A - Digital rural construction comprehensive service system based on big data - Google Patents
Digital rural construction comprehensive service system based on big data Download PDFInfo
- Publication number
- CN116703182A CN116703182A CN202310974842.6A CN202310974842A CN116703182A CN 116703182 A CN116703182 A CN 116703182A CN 202310974842 A CN202310974842 A CN 202310974842A CN 116703182 A CN116703182 A CN 116703182A
- Authority
- CN
- China
- Prior art keywords
- resident
- data
- village
- merging
- network
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000010276 construction Methods 0.000 title claims abstract description 20
- 238000000034 method Methods 0.000 claims abstract description 13
- 238000012549 training Methods 0.000 claims abstract description 9
- 238000013075 data extraction Methods 0.000 claims abstract description 5
- 238000007781 pre-processing Methods 0.000 claims abstract description 5
- 239000013598 vector Substances 0.000 claims description 27
- 238000010586 diagram Methods 0.000 claims description 8
- 239000011159 matrix material Substances 0.000 claims description 7
- 230000009466 transformation Effects 0.000 claims description 6
- 238000004364 calculation method Methods 0.000 claims description 4
- 230000004913 activation Effects 0.000 claims description 3
- 239000000284 extract Substances 0.000 claims description 3
- 238000005067 remediation Methods 0.000 description 5
- 230000001225 therapeutic effect Effects 0.000 description 4
- 238000004519 manufacturing process Methods 0.000 description 3
- 230000008901 benefit Effects 0.000 description 2
- 238000007726 management method Methods 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 230000001737 promoting effect Effects 0.000 description 1
- 238000009418 renovation Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 239000013589 supplement Substances 0.000 description 1
- 230000007704 transition Effects 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0637—Strategic management or analysis, e.g. setting a goal or target of an organisation; Planning actions based on goals; Analysis or evaluation of effectiveness of goals
- G06Q10/06375—Prediction of business process outcome or impact based on a proposed change
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Theoretical Computer Science (AREA)
- Educational Administration (AREA)
- Physics & Mathematics (AREA)
- Economics (AREA)
- General Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- Entrepreneurship & Innovation (AREA)
- Software Systems (AREA)
- Marketing (AREA)
- Development Economics (AREA)
- General Business, Economics & Management (AREA)
- Game Theory and Decision Science (AREA)
- Quality & Reliability (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Medical Informatics (AREA)
- Operations Research (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to the technical field of regional planning, and discloses a digital rural construction comprehensive service system based on big data, which comprises the following steps: the data acquisition module is used for acquiring village data and a land utilization planning chart; a data preprocessing module for generating a regional data network; a data extraction module for extracting first network data and second network data; the model training module is used for training the combined prediction model; the merging result prediction module is used for generating a land utilization planning chart after village merging according to a village merging plan, and then outputting the land application efficiency difference before and after village merging by using a trained merging prediction model; the method and the system can accurately judge the difference value of the farmland application efficiency after the village merging plan is implemented, and provide direct support for selecting a better village merging plan.
Description
Technical Field
The invention relates to the technical field of regional planning, in particular to a digital rural construction comprehensive service system based on big data.
Background
Chinese invention patent publication No. CN108009694a, entitled hollow village remediation potential hierarchical assessment system, discloses the following: the comprehensive land remediation potential evaluation system for the hollow village can comprehensively evaluate land remediation potential of the hollow village in each region of China after comprehensive remediation, and the maximum potential and the space distribution condition of the comprehensive remediation and supplement cultivated land of the hollow village are obtained through analysis for visual expression, so that scientific basis is provided for promoting the management, the management and the reasonable planning of the hollow village in China;
the comprehensive renovation potential of the hollow village refers to that under a certain productivity level, a series of measures are adopted in the planning period to split and merge the existing rural residential land, and the effective cultivated land area which is possibly increased is dug and submerged in the interior and transformed and reused. According to the achievable degree of the therapeutic potential, the therapeutic potential can be divided into theoretical therapeutic potential and realistic therapeutic potential. The theoretical potential is that under certain assumption conditions, the standard of land utilization of rural residents of established people is adopted, and the adjustable cultivated land area is theoretically remedied by the rural residents; the actual potential refers to the potential of newly increased cultivated land area which can be realized in a certain period under the constraint conditions of the prior natural environment, the economic and technical development level, the system supply and the like, and represents the possibility of rural residential point arrangement, the intensity of investment requirements of the rural residential points in the treatment process and the like;
when considering the theoretical potential of comprehensive treatment of hollow villages, the research actually focuses on the treatment potential of rural residents, and the land increasing potential is mainly obtained by arranging the effective cultivated land which can be increased and other lands which are suitable for cultivation and backup through reconstruction, village transition and merging and ecological immigration of the rural residents which are scattered at present.
The invention discloses a method for calculating the land increasing potential in an area through indexes such as a residence of people, a construction land of people and the like, but the land increasing potential in a simple area cannot represent the increase of the land increasing benefit which can be provided by a village splitting and combining point, and the land increasing potential which can be exerted by different village combining plans when the village splitting and combining point is carried out in the area is different.
Disclosure of Invention
The invention provides a digital rural construction comprehensive service system based on big data, which solves the technical problem that the selection of a rural merging plan cannot be provided with specific guidance in the related technology.
The invention provides a digital rural construction comprehensive service system based on big data, which comprises the following steps:
the data acquisition module is used for acquiring village data and a land utilization planning chart;
the data preprocessing module is used for generating a regional data network, the regional data network comprises nodes and edges connected with the nodes, the nodes represent villages, resident households, resident residents and very resident residents, and the edges exist between the nodes to represent the links between the nodes; generating node characteristics for the nodes;
the data extraction module is used for extracting first network data and second network data, the first network data is data of the regional data network before village merging, the second network data is data of the regional data network after village merging, the first network data and the second network data comprise an adjacency matrix and a node characteristic sequence, wherein the adjacency matrix represents the connection relation of nodes of the regional data network, and the node characteristic sequence is composed of node characteristic arrangement of the nodes of the regional data network;
the model training module is used for training a combined prediction model, the combined prediction model comprises a first hidden layer, a first convolution layer, a first logic layer, a second logic layer and a full connection layer, wherein two channels of the first hidden layer are respectively input with first network data and second network data, updated first network data and second network data are output, and the first logic layer extracts node characteristics representing residents from the updated first network data and second network data to splice, so that regional characteristic vectors are generated;
inputting a land utilization planning diagram before village merging by a first convolution layer, and outputting a first characteristic diagram; inputting a land utilization planning map after village merging by the first convolution layer, and outputting a second characteristic map; the second logic layer performs difference between the first feature map and the second feature map to obtain a third feature map, then performs vectorization on the third feature map to obtain a feature map vector, and then splices the feature map vector and the regional feature vector and inputs the spliced feature map vector and the regional feature vector into the full-connection layer; the application efficiency of cultivated land before and after the combination of the output villages of the full-connection layer is poor;
the merging result prediction module is used for generating a land utilization planning chart after village merging according to a village merging plan, and then outputting the land application efficiency difference before and after village merging by using a trained merging prediction model;
and the plan selection module is used for selecting the village merging plan with the largest farmland application efficiency difference as the village merging plan to be implemented.
Further, the village data includes data of villages, data of each resident of the households, and data of each resident.
Further, there is a relationship between a node of a village and all resident's belonging to the village, there is a relationship between a node of a resident's and a resident's belonging to the resident's, and the presence of a relationship between a resident's node and a resident's relationship indicates that there is a relationship between the resident's resident and the resident's relationship; the existence of a link between a resident's node and a resident indicates the existence of a relationship between the two residents.
Further, node characteristics of the a-th villageExpressed as: />Wherein->Indicates the total number of residents in the a-th village, < ->Representing the total number of resident in the a-th village，/>Indicates the number of a village, < ->Indicating the area of the home in the a-th village,/->Representing the planting cultivated land area of the a-th village;
node characteristics of the b th residentExpressed as: />Wherein->Representing the number of residents of the b th resident, < ->Representing the number of resident of the b-th resident, < > th resident>Indicating the number of very resident of the b-th resident,/->Indicating the residence area of the b th resident,/->Representing the planting cultivated area of the b th resident;
node characteristics of the c th residentExpressed as: />Wherein->Represent the firstPlanting cultivated land area of c resident residents, < ->Indicating the age of the c-th resident, < ->Non-business annual revenue representing the c-th resident;
node characteristics of the d very residentExpressed as: />Wherein->Representing the area of the contractual floor of the d-th very resident,/->Indicating the age of the d-th very resident, < ->Representing the annual revenue of non-service farmers for the d very resident.
Further, the calculation formula of the first hidden layer is:
；
wherein the method comprises the steps of，/>，/>，/>Node representing the ith node of the first network data or the second network data after updatingCharacteristic(s)>And->Node characteristics of the i and j th nodes representing the first network data or the second network data, respectively, before the update,/->Representation->Intermediate features obtained by linear transformation, < >>Representation->Intermediate features obtained by linear transformation, < >>Weight parameter representing the first hidden layer, +.>Weight vector representing the first hidden layer, +.>Representing a set of nodes with edge connections to the ith node,/for>Representing an activation function->Representing the attention weight.
Further, the land use plan entered by the first convolution layer includes an area of the area data network.
Further, the full link layer outputs a value indicating that the cultivated land application efficiency is poor or a class label, and if the class label is output, the class label of the classification space of the full link layer maps the point value of the value range that the cultivated land application efficiency is poor.
Further, the element of the v-th row and s-th column of the third feature map is equal to the difference between the element of the v-th row and s-th column of the second feature map and the element of the v-th row and s-th column of the first feature map.
Further, the regional data network after village merging when the merging prediction model is trained is generated according to the historical data; the regional data network after village merging when the merging prediction model predicts is generated according to the village merging plan predicted as required and the current village data.
The invention has the beneficial effects that: the invention processes village and town data by using a deep learning method, can accurately judge the difference value of the farmland application efficiency after the village and town combination plan is implemented, and provides direct support for selecting a better village and town combination plan.
Drawings
FIG. 1 is a schematic diagram of a digital rural construction integrated service system based on big data;
fig. 2 is a schematic diagram of a module II of the digital rural construction integrated service system based on big data.
In the figure: the system comprises a data acquisition module 101, a data preprocessing module 102, a data extraction module 103, a model training module 104, a merging result prediction module 105 and a plan selection module 106.
Detailed Description
The subject matter described herein will now be discussed with reference to example embodiments. It is to be understood that these embodiments are merely discussed so that those skilled in the art may better understand and implement the subject matter described herein and that changes may be made in the function and arrangement of the elements discussed without departing from the scope of the disclosure herein. Various examples may omit, replace, or add various procedures or components as desired. In addition, features described with respect to some examples may be combined in other examples as well.
As shown in fig. 1, a digital rural construction integrated service system based on big data includes:
a data acquisition module 101 for acquiring village data including data of villages, data of each resident of households, and data of each resident, and a land use plan.
A data preprocessing module 102 for generating a regional data network, the regional data network including nodes representing villages, resident households, resident residents, and very resident residents and edges connecting the nodes, the edges between the nodes representing links between the nodes; generating node characteristics for the nodes;
the data can be obtained by means of interview investigation and the like.
In one embodiment of the invention, there is a connection between a node of a village and all resident's belonging to the village, a connection between a node of a resident's and resident's belonging to the resident's, the existence of a link between a resident's node and a resident's relationship indicates the existence of a relationship between the resident and the resident; the existence of a link between a resident's node and a resident indicates the existence of a relationship between the two residents.
The area of the regional data network may be an administrative area in villages or counties.
Resident is not counted only through the apartment, and the resident is defined as resident only when the annual residence time exceeds 6 months.
Node characteristics of the a-th villageExpressed as: />Wherein->Indicates the total number of residents in the a-th village, < ->Indicating the total number of resident in the a-th village, < ->Indicates the number of a village, < ->Indicating the area of the home in the a-th village,/->Representing the area of cultivated land for the a-th village.
Node characteristics of the b th residentExpressed as: />Wherein->Representing the number of residents of the b th resident, < ->Representing the number of resident of the b-th resident, < > th resident>Indicating the number of very resident of the b-th resident,/->Indicating the residence area of the b th resident,/->Representing the cultivated land area of the b-th resident.
Node characteristics of the c th residentExpressed as: />Wherein->Representing the cultivated land area of the c-th resident +.>Indicating the age of the c-th resident, < ->Non-business annual revenue representing the c-th resident;
node characteristics of the d very residentExpressed as: />Wherein->Representing the area of the contractual floor of the d-th very resident,/->Indicating the age of the d-th very resident, < ->Representing the annual revenue of non-service farmers for the d very resident.
The values of the components of the node features are derived from the acquired village data, and the present invention does not exclude other ways of constructing the node features from the village data.
A data extraction module 103, configured to extract first network data and second network data, where the first network data is data of an area data network before the merging, the second network data is data of an area data network after the merging, and the first network data and the second network data each include an adjacency matrix and a node feature sequence, where the adjacency matrix represents a connection relationship of nodes of the area data network, and the node feature sequence is composed of node feature arrangements of nodes of the area data network;
the element of the kth row and the kth column of the adjacency matrix represents the connection relation between the kth and the ith node, if an edge exists between the kth and the ith node, the value of the element is 1, otherwise, the value of the element is 0; the kth sequence element of the node characteristic sequence represents the node characteristic of the kth node.
The model training module 104 is configured to train a merged prediction model, where the merged prediction model includes a first hidden layer, a first convolution layer, a first logic layer, a second logic layer, and a full connection layer, two channels of the first hidden layer respectively input first network data and second network data, output updated first network data and second network data, and the first logic layer extracts node features representing residents from the updated first network data and second network data, and performs stitching to generate an area feature vector;
inputting a land utilization planning diagram before village merging by a first convolution layer, and outputting a first characteristic diagram; inputting a land utilization planning map after village merging by the first convolution layer, and outputting a second characteristic map; the second logic layer performs difference between the first feature map and the second feature map to obtain a third feature map, then performs vectorization on the third feature map to obtain a feature map vector, and then splices the feature map vector and the regional feature vector and inputs the spliced feature map vector and the regional feature vector into the full-connection layer;
the element of the v-th row and the s-th column of the third feature map is equal to the difference value between the element of the v-th row and the s-th column of the second feature map and the element of the v-th row and the s-th column of the first feature map.
Vectorizing the third feature map is to splice row vectors of the third feature map in row order.
The method for extracting the node characteristics representing the resident from the updated first network data and the updated second network data for splicing comprises the following steps: the method comprises the steps of firstly splicing the node characteristics of the updated first network data representing the residents in sequence to generate a first area vector, splicing the node characteristics of the updated second network data representing the residents in sequence to generate a second area vector, and then splicing the first area vector and the second area vector to obtain an area characteristic vector.
In one embodiment of the present invention, an ID is assigned to each resident's node when the first network data and the second network data are established, and splicing is performed in the order of the IDs.
The application efficiency of the cultivated land before and after the combination of the output villages of the full-connection layer is poor.
The calculation formula of the first hidden layer is:；
wherein the method comprises the steps of，/>，/>，/>Node characteristic of the i-th node representing the first network data or the second network data after updating, a->And->Node characteristics of the i and j th nodes representing the first network data or the second network data, respectively, before the update,/->Representation->Intermediate features obtained by linear transformation, < >>Representation->Intermediate features obtained by linear transformation, < >>Weight parameter representing the first hidden layer, +.>Weight vector representing the first hidden layer, +.>Representing a set of nodes with edge connections to the ith node,/for>Representing an activation function->Represents an attention weight;
the first convolution layer may employ LetNet, alexNet or ResNet.
In one embodiment of the invention, the land utilization map input by the first convolutional layer includes an area of the regional data network.
In one embodiment of the present invention, the full link layer outputs a value indicating that the cultivated land application efficiency is poor or a class label, and if the class label is output, the class label of the classification space of the full link layer maps the point value of the value range of the cultivated land application efficiency poor.
The tilling efficiency difference is equal to the difference between the tilling efficiency after the village merger and the tilling efficiency before the village merger;
efficiency of tilling application during trainingThe calculation formula of (2) is as follows:
wherein the method comprises the steps ofFor the efficiency value of the jth resident, < +.>Planting cultivated land area for jth resident,/->And m is the total planting cultivated land area in the statistical area, and m is the total number of resident households in the statistical area.
Wherein the method comprises the steps of，/>，/>Input value of the ith input item for the jth resident,/for the jth input item>Yield value of the (th) yield item for the (th) resident, +.>And->Weights of the (r) th production item and the (i) th input item, respectively,/->The weight of the j-th production item is represented, s and n are the number of the production item and the input item respectively, +.>The efficiency value of the jth resident.
And a merging result prediction module 105 for generating a land use plan map after the village merge according to the village merge plan, and then outputting a farmland application efficiency difference before and after the village merge using the trained merging prediction model.
The regional data network after village merging when the merging prediction model is trained is generated according to historical data, wherein the historical data refers to village and town data of villages and towns after village merging is performed; the regional data network after village merging when the merging prediction model predicts is generated according to the village merging plan predicted as required and the current village data. For example, after the village merging, the attribution of the resident can be adjusted according to the village merging plan, and the village merging plan is an artificially planned village merging plan.
As shown in fig. 2, in one embodiment of the present invention, a digitized rural construction integrated service system based on big data further includes a plan selection module 106 for selecting a village merge plan with the greatest efficiency of cultivated land application as the village merge plan to be implemented.
The embodiment has been described above with reference to the embodiment, but the embodiment is not limited to the above-described specific implementation, which is only illustrative and not restrictive, and many forms can be made by those of ordinary skill in the art, given the benefit of this disclosure, are within the scope of this embodiment.
Claims (9)
1. A digital rural construction integrated service system based on big data, comprising:
the data acquisition module is used for acquiring village data and a land utilization planning chart;
the data preprocessing module is used for generating a regional data network, the regional data network comprises nodes and edges connected with the nodes, the nodes represent villages, resident households, resident residents and very resident residents, and the edges exist between the nodes to represent the links between the nodes; generating node characteristics for the nodes;
the data extraction module is used for extracting first network data and second network data, the first network data is data of the regional data network before village merging, the second network data is data of the regional data network after village merging, the first network data and the second network data comprise an adjacency matrix and a node characteristic sequence, wherein the adjacency matrix represents the connection relation of nodes of the regional data network, and the node characteristic sequence is composed of node characteristic arrangement of the nodes of the regional data network;
the model training module is used for training a combined prediction model, the combined prediction model comprises a first hidden layer, a first convolution layer, a first logic layer, a second logic layer and a full connection layer, wherein two channels of the first hidden layer are respectively input with first network data and second network data, updated first network data and second network data are output, and the first logic layer extracts node characteristics representing residents from the updated first network data and second network data to splice, so that regional characteristic vectors are generated;
inputting a land utilization planning diagram before village merging by a first convolution layer, and outputting a first characteristic diagram; inputting a land utilization planning map after village merging by the first convolution layer, and outputting a second characteristic map; the second logic layer performs difference between the first feature map and the second feature map to obtain a third feature map, then performs vectorization on the third feature map to obtain a feature map vector, and then splices the feature map vector and the regional feature vector and inputs the spliced feature map vector and the regional feature vector into the full-connection layer; the application efficiency of cultivated land before and after the combination of the output villages of the full-connection layer is poor;
the merging result prediction module is used for generating a land utilization planning chart after village merging according to a village merging plan, and then outputting the land application efficiency difference before and after village merging by using a trained merging prediction model;
and the plan selection module is used for selecting the village merging plan with the largest farmland application efficiency difference as the village merging plan to be implemented.
2. The digital rural construction integrated service system according to claim 1 wherein the village data comprises village data, resident data of each household, and resident data of each resident.
3. The digital rural construction integrated service system according to claim 1 wherein the node of the village is associated with all resident's family members belonging to the village, the node of resident's family members is associated with resident's family members belonging to the resident's family members, and the association between the resident's node and the resident's family members indicates the relationship between the resident's family members and the resident's family members; the existence of a link between a resident's node and a resident indicates the existence of a relationship between the two residents.
4. The digital rural construction integrated service system based on big data according to claim 1, wherein the node characteristics of the a-th villageExpressed as: />Wherein->Indicates the total number of residents in the a-th village, < ->Indicating the total number of resident in the a-th village, < ->Indicates the number of a village, < ->Indicating the area of the home in the a-th village,/->Representing the planting cultivated land area of the a-th village;
node characteristics of the b th residentExpressed as: />Wherein->Representing the number of residents of the b th resident, < ->Representing the number of resident of the b-th resident, < > th resident>Indicating the number of very resident of the b-th resident,/->Indicating the residence area of the b th resident,/->Representing the planting cultivated area of the b th resident;
node characteristics of the c th residentExpressed as: />Wherein->Representing the cultivated land area of the c-th resident +.>Indicating the age of the c-th resident, < ->Non-business annual revenue representing the c-th resident;
node characteristics of the d very residentExpressed as: />Wherein->Representing the area of the contractual floor of the d-th very resident,/->Indicating the age of the d-th very resident, < ->Representing the annual revenue of non-service farmers for the d very resident.
5. The digital rural construction integrated service system based on big data according to claim 1, wherein the calculation formula of the first hidden layer is:；
wherein the method comprises the steps of，/>，/>，/>Node characteristic of the i-th node representing the first network data or the second network data after updating, a->And->Node characteristics of the i and j th nodes representing the first network data or the second network data, respectively, before the update,/->Representation->Intermediate features obtained by linear transformation, < >>Representation->Intermediate features obtained by linear transformation, < >>Weight parameter representing the first hidden layer, +.>Weight vector representing the first hidden layer, +.>Representing a set of nodes with edge connections to the ith node,/for>Representing an activation function->Representing the attention weight.
6. The digital rural construction integrated service system based on big data according to claim 1, wherein the land use plan inputted by the first convolution layer comprises an area of the regional data network.
7. The digital rural construction integrated service system based on big data according to claim 1, wherein the full connection layer outputs a value indicating poor efficiency of application of cultivated land or a class label, and if the class label is outputted, the class label of the classification space of the full connection layer maps a point value of a range of poor efficiency of application of cultivated land.
8. The digitized country construction integrated service system of claim 1 wherein the elements of the third signature in the v-th row and s-th column are equal to the difference between the elements of the second signature in the v-th row and s-th column and the elements of the first signature in the v-th row and s-th column.
9. The digital rural construction integrated service system based on big data according to claim 1, wherein the regional data network after the village merging when the merging prediction model is trained is generated according to the historical data; the regional data network after village merging when the merging prediction model predicts is generated according to the village merging plan predicted as required and the current village data.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310974842.6A CN116703182B (en) | 2023-08-04 | 2023-08-04 | Digital rural construction comprehensive service system based on big data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310974842.6A CN116703182B (en) | 2023-08-04 | 2023-08-04 | Digital rural construction comprehensive service system based on big data |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116703182A true CN116703182A (en) | 2023-09-05 |
| CN116703182B CN116703182B (en) | 2023-10-20 |
Family
ID=87832544
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310974842.6A Active CN116703182B (en) | 2023-08-04 | 2023-08-04 | Digital rural construction comprehensive service system based on big data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116703182B (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105512661A (en) * | 2015-11-25 | 2016-04-20 | 中国人民解放军信息工程大学 | Multi-mode-characteristic-fusion-based remote-sensing image classification method |
| CN107248007A (en) * | 2017-06-02 | 2017-10-13 | 武汉大学 | The rural residential area intelligent optimization collocation method that a kind of double-deck domain is oriented to |
| EP3614308A1 (en) * | 2018-08-24 | 2020-02-26 | Ordnance Survey Limited | Joint deep learning for land cover and land use classification |
| CN113469226A (en) * | 2021-06-16 | 2021-10-01 | 中国地质大学（武汉） | Street view image-based land utilization classification method and system |
| CN113987893A (en) * | 2021-12-29 | 2022-01-28 | 北京大学深圳研究生院 | Villages and small towns colony system derived network analysis system |
| US20220036198A1 (en) * | 2020-07-28 | 2022-02-03 | International Business Machines Corporation | Fixed, random, recurrent matrices for increased dimensionality in neural networks |
| CN115526418A (en) * | 2022-10-17 | 2022-12-27 | 东南大学 | Country ecological space prediction method based on Bayesian network |
-
2023
- 2023-08-04 CN CN202310974842.6A patent/CN116703182B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105512661A (en) * | 2015-11-25 | 2016-04-20 | 中国人民解放军信息工程大学 | Multi-mode-characteristic-fusion-based remote-sensing image classification method |
| CN107248007A (en) * | 2017-06-02 | 2017-10-13 | 武汉大学 | The rural residential area intelligent optimization collocation method that a kind of double-deck domain is oriented to |
| EP3614308A1 (en) * | 2018-08-24 | 2020-02-26 | Ordnance Survey Limited | Joint deep learning for land cover and land use classification |
| US20220036198A1 (en) * | 2020-07-28 | 2022-02-03 | International Business Machines Corporation | Fixed, random, recurrent matrices for increased dimensionality in neural networks |
| CN113469226A (en) * | 2021-06-16 | 2021-10-01 | 中国地质大学（武汉） | Street view image-based land utilization classification method and system |
| CN113987893A (en) * | 2021-12-29 | 2022-01-28 | 北京大学深圳研究生院 | Villages and small towns colony system derived network analysis system |
| CN115526418A (en) * | 2022-10-17 | 2022-12-27 | 东南大学 | Country ecological space prediction method based on Bayesian network |
Non-Patent Citations (2)
| Title |
|---|
| JIANKAI ZUO 等: "Artificial Intelligence Prediction and Decision Evaluation Model Based on Deep Learning", 2019 INTERNATIONAL CONFERENCE ON ELECTRONIC ENGINEERING AND INFORMATICS (EEI) * |
| 姚柳杨;赵敏娟;徐涛;: "耕地保护政策的社会福利分析:基于选择实验的非市场价值评估", 农业经济问题, no. 02 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116703182B (en) | 2023-10-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Sánchez-Lozano et al. | GIS-based photovoltaic solar farms site selection using ELECTRE-TRI: Evaluating the case for Torre Pacheco, Murcia, Southeast of Spain | |
| Medvedev et al. | Medium-term analysis of agroecosystem sustainability under different land use practices by means of dynamic crop simulation | |
| Wang et al. | A GIS-based approach in support of spatial planning for renewable energy: A case study of Fukushima, Japan | |
| Wichmann et al. | Homelands of the world’s language families: A quantitative approach | |
| CN102495919B (en) | Extraction method for influence factors of carbon exchange of ecosystem and system | |
| CN104820707A (en) | Automatic test paper composition method in B/S (Brower/Server) mode based on knowledge hierarchy in field of computers | |
| CN110162872B (en) | Biomass estimation method fusing sample plot data and forest resource clearing data | |
| CN114092832A (en) | High-resolution remote sensing image classification method based on parallel hybrid convolutional network | |
| CN107680018A (en) | A kind of college entrance will based on big data and artificial intelligence makes a report on system and method | |
| CN110298520A (en) | A kind of farmland construction difficulty determines method | |
| Raheem et al. | Sustainable rural development programmes in Nigeria: Issues and challenges | |
| CN109670042A (en) | A kind of examination question classification and grade of difficulty method based on recurrent neural network | |
| CN116703182B (en) | Digital rural construction comprehensive service system based on big data | |
| CN106844642A (en) | A kind of method that the density of population in road network grid is calculated based on GIS | |
| CN106651017A (en) | Method for site selection of land consolidation project based on ant colony optimization algorithm | |
| Zhao et al. | Neighborhood micro-renewal: a perspective of gene in China | |
| CN105279388A (en) | Multilayer cloud computing framework coordinated integrated reduction method for gestational-age newborn brain medical records | |
| Phoksawat et al. | Knowledge and integrated data management model for personalized intercropping in rubber plantation. | |
| CN104679836A (en) | Automatic extension method of agricultural ontology | |
| CN109815374A (en) | Low-voltage distribution network platform region title similarity matching methods and matching system | |
| Pavlov et al. | Irrigation performance assessment in Crimea, Ukraine | |
| Pratiwi et al. | Study on Implementation of Special Efforts to Increase Production of Rice, Corn, Soy (Upsus Pajale) in Cakranegara District, Mataram City | |
| Nyakudya et al. | A decision support tool for rural electrification grid design | |
| Tiwari et al. | Predicting Future Urban Growth in Bhopal, India using Artificial Intelligence based Modelling | |
| Umetsu et al. | The Role of Efficient Management of Water Users’ Associations for Adapting to Future Water Scarcity Under Climate Change |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |